© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1942
    Prev
    Next
    INDEX
    Explanations

    units after quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    //!
    -0.98
     motoru
    -0.97
     engineers
    -0.94
     musíte
    -0.94
     maail
    -0.90
     subray
    -0.90
     ň
    -0.90
     št
    -0.88
     solusi
    -0.88
     Manajemen
    -0.87
    POSITIVE LOGITS
     marmor
    0.98
     itali
    0.94
    Internal
    0.90
     crede
    0.90
     patria
    0.88
    每
    0.86
    Kontrola
    0.85
     pép
    0.85
     bure
    0.83
     determinations
    0.83
    Activations Density 0.019%

    No Known Activations